Remaining Useful Life Prediction using Dynamic Principal Component Analysis and Deep Gated Recurrent Unit Network

Massive multi-sensor data makes it challenging to extract degradation features and predict the remaining useful life (RUL). This paper introduces a novel RUL prediction method using dynamic principal component analysis (DPCA) and deep gated recurrent unit (DGRU) network. DPCA is utilized to construct the health index (HI) curve considering autocorrelation. DGRU network is built to predict the RUL ...